Digital Model Identification Method Based on Avionics System

Abstract

The present invention discloses a digital model identification method based on an avionics system, belonging to the technical field of avionics systems, and comprising the following steps: S1: constructing a digital model of the avionics system and determining the influencing factors of the avionics system for digital model identification; S2: performing simulation analysis on the digital model of the avionics system and determining the simulation analysis results of the digital model of the avionics system; S3: performing digital model identification on the simulation analysis results of the digital model of the avionics system and determining the digital model identification results of the avionics system; S4: generating an optimization report for the digital model identification of the avionics system and timely solving the abnormal problems of the digital model of the avionics system. The present invention solves the problems that the existing method cannot effectively identify the digital model of the avionics system, cannot timely discover and solve abnormal problems, resulting in poor use effects. The present invention can effectively identify the digital model of the avionics system, can timely discover and solve abnormal problems, and can improve the use effects.

Description

Technical Field

[0001] The present invention relates to the technical field of avionics systems, and specifically to a digital model identification method based on avionics systems. Background Technique

[0002] The traditional aircraft design and manufacturing methods can no longer meet the requirements of modern aircraft for flight performance and reliability; therefore, the adoption of digital design has become the current trend in the development of the aviation industry; in aircraft systems, the avionics system is a crucial component, and its performance directly affects flight safety. Therefore, identifying the digital model of the avionics system to ensure its reliability and stability under various working conditions is of great significance for improving flight safety and reducing operating costs.

[0003] Chinese Patent with Publication No. CN115185493A discloses a model-based avionics system architecture design method, including the following steps: determining the design requirements of the avionics system architecture; respectively establishing meta-models required in the avionics system field in the function layer, logic layer, physical layer, and message layer; constructing a mapping matrix between the design requirements and functions, designing the layer models of each layer, establishing the vertical mapping relationship between each layer model, and forming a complete avionics system architecture model; carrying out avionics system architecture design modeling according to the design requirements and the meta-models of each layer field, comprehensively implementing and covering the requirements, and configuring resources on the multi-layer model to ensure that the current system architecture can meet requirements such as safety, reliability, and real-time performance; however, this patent has the following defects:

[0004] The existing method cannot effectively identify the digital model of the avionics system, cannot timely discover and solve abnormal problems, resulting in poor use effects. Summary of the Invention

[0005] The purpose of the present invention is to provide a digital model identification method based on avionics systems, which can effectively identify the digital model of the avionics system, can timely discover and solve abnormal problems, can improve the use effect, and solves the problems raised in the above background technique.

[0006] To achieve the above purpose, the present invention provides the following technical solution:

[0007] A digital model identification method based on avionics systems includes the following steps:

[0008] S1: Using modeling software and mathematical tools, construct a digital model of the avionics system, define identification rules, and determine the influencing factors of the avionics system for digital model identification;

[0009] S2: Based on different influencing factors of the avionics system for digital model identification, conduct simulation analysis on the digital model of the avionics system to determine the simulation analysis results of the digital model of the avionics system;

[0010] S3: Based on the avionics system digital model simulation analysis standard, conduct digital model identification on the avionics system digital model simulation analysis results to determine the avionics system digital model identification results;

[0011] S4: Based on the avionics system digital model identification results, generate an avionics system digital model identification optimization report to intelligently guide managers to adjust and optimize the avionics system digital model and timely solve the abnormal problems of the avionics system digital model.

[0012] Preferably, in S1, to construct the avionics system digital model, the following operations are performed:

[0013] Collect the hardware specifications and software configuration parameters of the avionics system to determine the avionics system design parameters;

[0014] Process the avionics system design parameters to determine the avionics system characteristic data;

[0015] Based on the avionics system characteristic data, and using modeling software and mathematical tools, conduct three-dimensional modeling on the avionics system to determine the avionics system digital model.

[0016] Preferably, in S1, to process the avionics system design parameters, the following operations are performed:

[0017] Obtain the avionics system design parameters;

[0018] Conduct cleaning processing on the avionics system design parameters, including:

[0019] Conduct consistency check on the avionics system design parameters;

[0020] According to the data consistency requirements, remove the inconsistent data in the avionics system design parameters that are useless for the digital model identification of the avionics system;

[0021] Conduct invalid value and missing value processing on the avionics system design parameters;

[0022] According to the data validity and integrity requirements, remove the invalid values and missing values in the avionics system design parameters that are useless for the digital model identification of the avionics system, and determine the avionics system design parameters that are useful for the digital model identification of the avionics system;

[0023] Obtain the avionics system design parameters that are useful for the digital model identification of the avionics system;

[0024] Conduct feature extraction on the avionics system design parameters that are useful for the digital model identification of the avionics system;

[0025] Extract the features that can reflect the digital model identification of the avionics system;

[0026] Determine the characteristic data of the avionics system for departure.

[0027] Preferably, to remove the invalid values and missing values that are useless for the identification of the digital model based on the avionics system from the design parameters of the avionics system, the following operations are performed:

[0028] After removing the useless invalid values and missing values, extract the number of data of the design parameters of the avionics system that are useful for the identification of the digital model based on the avionics system;

[0029] Compare the number of data with a preset data number threshold;

[0030] When the number of data is lower than the preset data number threshold, then extract the weight values of the removed invalid values and missing values;

[0031] Extract the weight values of the valid values closest to the data generation time of the removed invalid values and missing values;

[0032] Use the weight values of the removed invalid values and missing values in combination with the weight values of the valid values closest to the data generation time of the removed invalid values and missing values to obtain a weight value threshold;

[0033] Among them, the weight value threshold is obtained through the following formula:

[0034]

[0035] Among them, S represents the weight value threshold; n represents the number of removed invalid values; m represents the number of removed missing values; w 01i represents the weight value of the i-th removed invalid value; w 01xi represents the weight value of the valid value closest to the data generation time of the i-th removed invalid value; w 02i represents the weight value of the i-th removed missing value; w 02xi represents the weight value of the valid value closest to the data generation time of the i-th removed missing value; E 01 and E 02 respectively represent the first adjustment coefficient and the second adjustment coefficient, and, the first adjustment coefficient is obtained through the following formula:

[0036]

[0037] Among them, E 01 represents the first adjustment coefficient; w 01z represents the median of the weight values of the n removed invalid values; w 01xz represents the median of the weight values of the valid values closest to the data generation time corresponding to the n removed invalid values;

[0038] Meanwhile, the second adjustment coefficient is obtained through the following formula:

[0039]

[0040] where E 02 represents the second adjustment coefficient; w 02z represents the median of the weight values of m removed missing values; w 02xz represents the median of the weight values of the valid values closest to the data generation times corresponding to the m removed missing values;

[0041] Compare the weight values corresponding to the invalid values and missing values with a preset weight value threshold, obtain the filling values corresponding to the invalid values and missing values through the comparison results, and use the filling values corresponding to the invalid values and missing values to fill the corresponding invalid values and missing values.

[0042] Preferably, compare the weight values corresponding to the invalid values and missing values with a preset weight value threshold, obtain the filling values corresponding to the invalid values and missing values through the comparison results, and use the filling values corresponding to the invalid values and missing values to fill the corresponding invalid values and missing values, and perform the following operations:

[0043] Compare the weight value of the invalid value with the weight value threshold, and extract the invalid values corresponding to the weight values exceeding the weight value threshold as target invalid values;

[0044] Extract the valid values with the same weight values as each target invalid value from the valid values as the first reference valid values;

[0045] Extract the data generation time intervals between the first reference valid values and each target invalid value;

[0046] Use the data values of the first reference valid values combined with the data generation time intervals between the first reference valid values and each target invalid value to obtain the filling values corresponding to each target invalid value;

[0047] Among them, the filling value corresponding to each target invalid value is obtained through the following formula:

[0048]

[0049] where X w represents the filling value corresponding to each target invalid value; a represents the number of data of the first reference valid value corresponding to each target invalid value; X 01i represents the data value of the i-th first reference valid value; X 01i+1 represents the data value of the (i + 1)-th first reference valid value; X 01bThe standard deviation of data values representing a first reference valid value; T g01i The data generation time interval between the i-th first reference valid value and each target invalid value;

[0050] Fill the target invalid values with the filling values corresponding to each of the target invalid values.

[0051] Preferably, compare the weight values corresponding to the invalid values and missing values with a preset weight value threshold, obtain the filling values corresponding to the invalid values and missing values through the comparison result, and fill the corresponding invalid values and missing values with the filling values corresponding to the invalid values and missing values, and also perform the following operations:

[0052] Compare the weight value of the missing value with the weight value threshold, and extract the missing values corresponding to the weight values exceeding the weight value threshold as target missing values;

[0053] Extract the valid values with the same weight value as each target missing value from the valid values as the second reference valid values;

[0054] Extract the filled target invalid values with the same weight value as the target missing value as the third reference valid values;

[0055] Extract the data generation time intervals between the second reference valid values and the third reference valid values and each target missing value;

[0056] Use the second reference valid values and the third reference valid values in combination with the data generation time intervals between the second reference valid values and the third reference valid values and each target missing value to obtain the filling values corresponding to each target missing value;

[0057] Among them, the filling value corresponding to each target missing value is obtained through the following formula:

[0058]

[0059] Among them, X q Represents the filling value corresponding to each target missing value; b represents the number of data of the second reference valid values; c represents the number of data of the third reference valid values; X 02i Represents the data value of the i-th second reference valid value; X wi Represents the data value of the i-th third reference valid value; T g02i Represents the data generation time interval between the i-th second reference valid value and each target missing value; T g03i Represents the data generation time interval between the i-th third reference valid value and each target missing value; X 02zThe data value median representing b second reference valid values; X wz The data value median representing c third reference valid values; X wb The data value standard deviation representing c third reference valid values; X wp The data value average representing c third reference valid values; X 02b The data value standard deviation representing b second reference valid values; X 02p The data value average representing b second reference valid values;

[0060] Fill the target missing values with the filling values corresponding to each of the target missing values.

[0061] Preferably, in S1, to determine the influencing factors of the avionics system identified by the digital model, perform the following operations:

[0062] According to the structure and function of the avionics system digital model, combined with the actual flight conditions of the aircraft, define the identification rules, check whether the avionics system digital model can correctly implement all expected functions, comprehensively consider which factors will affect the behavior of the avionics system, and determine the influencing factors of the avionics system identified by the digital model;

[0063] Among them, the influencing factors of the avionics system identified by the digital model include: speed, altitude, load, temperature, pressure, and electromagnetic interference.

[0064] Preferably, in S2, to determine the simulation analysis results of the avionics system digital model, perform the following operations:

[0065] Obtain the influencing factors of the avionics system identified by the digital model;

[0066] Input the different influencing factors of the avionics system identified by the digital model into the avionics system digital model;

[0067] Based on the different influencing factors of the avionics system identified by the digital model, conduct simulation analysis on the avionics system digital model, and determine the simulation analysis results of the avionics system digital model by comparing the performance of the avionics system under different influencing factors of the avionics system.

[0068] Preferably, in S3, to determine the identification results of the avionics system digital model, perform the following operations:

[0069] According to the digital model identification requirements of the avionics system, preset the simulation analysis criteria for the avionics system digital model, and store the preset simulation analysis criteria for the avionics system digital model;

[0070] According to the identification requirements of the digital model of the avionics system, index the stored avionics system digital model simulation analysis standards, and retrieve the indexed avionics system digital model simulation analysis standards;

[0071] Based on the avionics system digital model simulation analysis standards, conduct digital model identification on the avionics system digital model simulation analysis results to determine the avionics system digital model identification results.

[0072] Preferably, in step S3, based on the avionics system digital model simulation analysis standards, conducting digital model identification on the avionics system digital model simulation analysis results includes:

[0073] When the avionics system digital model simulation analysis results are within the range of the avionics system digital model simulation analysis standards, the avionics system digital model identification result is that the avionics system digital model is normal and can correctly implement all expected functions;

[0074] When the avionics system digital model simulation analysis results are not within the range of the avionics system digital model simulation analysis standards, the avionics system digital model identification result is that the avionics system digital model is abnormal and cannot correctly implement all expected functions.

[0075] Preferably, in step S4, the intelligent system guides the management personnel to adjust and optimize the avionics system digital model, and performs the following operations:

[0076] Obtain the avionics system digital model identification results;

[0077] Based on the avionics system digital model identification results, conduct mining analysis on the avionics system digital model to generate an avionics system digital model identification optimization report;

[0078] Transmit the avionics system digital model identification optimization report to the management personnel in a visual form, and the intelligent system guides the management personnel to adjust and optimize the avionics system digital model to promptly solve the abnormal problems of the avionics system digital model.

[0079] Compared with the prior art, the beneficial effects of the present invention are:

[0080] 1. The present invention uses modeling software and mathematical tools to construct an avionics system digital model. According to the structure and functions of the avionics system digital model, combined with the actual flight conditions of the aircraft, define identification rules, determine the avionics system influencing factors for digital model identification, and conduct simulation analysis on the avionics system digital model based on different avionics system influencing factors for digital model identification to determine the avionics system digital model simulation analysis results.

[0081] 2. Based on the digital model simulation analysis standard of the avionics system, this invention conducts digital model identification on the simulation analysis results of the avionics system digital model, determines the digital model identification results of the avionics system, and generates an optimization report for the digital model identification of the avionics system, intelligently guiding managers to adjust and optimize the avionics system digital model, timely solving the abnormal problems of the avionics system digital model, enabling effective identification of the avionics system digital model, promptly discovering and solving abnormal problems, and improving the usage effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Figure 1 It is the operation flowchart of the digital model identification method for the avionics system based on this invention;

[0083] Figure 2 It is the algorithm flowchart for conducting digital model identification on the simulation analysis results of the avionics system digital model based on the digital model simulation analysis standard of the avionics system in this invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0084] Next, the technical solutions in the embodiments of this invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this invention. Obviously, the described embodiments are only a part of the embodiments of this invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of this invention without creative efforts shall fall within the scope of protection of this invention.

[0085] To solve the problem that the existing technology cannot effectively identify the digital model of the avionics system, cannot promptly discover and solve abnormal problems, resulting in poor usage effect, please refer to Figure 1 - Figure 2 , this embodiment provides the following technical solutions:

[0086] The digital model identification method for the avionics system includes the following steps:

[0087] S1: Using modeling software and mathematical tools, construct the avionics system digital model, define the identification rules, and determine the influencing factors of the avionics system for digital model identification;

[0088] In this embodiment, when constructing the avionics system digital model, the following operations are performed:

[0089] Collect the hardware specifications and software configuration parameters of the avionics system, and determine the avionics system design parameters;

[0090] Process the avionics system design parameters to determine the avionics system characteristic data;

[0091] Based on the avionics system characteristic data, and using modeling software and mathematical tools, conduct three-dimensional modeling of the avionics system to determine the avionics system digital model.

[0092] It should be noted that on modern aircraft, a unified processor is used to uniformly process the information of various avionics devices on the aircraft, and devices with the same or similar functions are combined into one component, and relevant parameters are comprehensively displayed on the display. Information is transmitted between various avionics devices through an on-board data bus, so that the performance of all avionics devices on the entire aircraft reaches a higher level. Such a system is called an avionics system; the development of avionics systems has gone through several important stages, from the initial discrete structure, to the centralized structure, then to the integrated structure, and finally to the current highly integrated structure. This development has made avionics systems more intelligent and efficient, greatly enhancing the performance and safety of aircraft.

[0093] Specifically, the avionics system mainly includes the following parts: 1) Communication system: responsible for voice and data transmission between the aircraft and the outside, ensuring stable communication between the aircraft and the ground; 2) Navigation system: real-time collects and measures the motion information of the aircraft through various navigation sensors to ensure the safety and accuracy of flight; 3) Display system: provides comprehensive and clear flight information display for the flight crew to help the flight crew accurately and timely grasp the flight dynamics and aircraft operating conditions; 4) Flight control system: responsible for the stability and maneuverability of the aircraft to ensure the stability and safety of the aircraft under various flight conditions; 5) Weather radar: used to detect weather conditions during flight to help pilots make appropriate flight decisions; 6) Aircraft management system: comprehensively manages various functions of the aircraft to ensure the overall performance and efficiency of the aircraft.

[0094] Among them, the hardware specifications of the avionics system mainly include the following aspects: 1) Display component: The multifunctional displays in the avionics system supporting equipment are available in various sizes, including 10.4 inches, 8 inches, and 6 inches. The display screen is a TFT panel with an anti-reflection function and can be clearly readable even in direct sunlight; their resolutions are 1024×768, 800×640, and 640×480 respectively; 2) Communication component: Atmospheric data computer: used to measure the static pressure, total pressure, and external atmospheric temperature of the aircraft during flight, calculate and output parameters such as indicated airspeed, true airspeed, relative pressure altitude, absolute pressure altitude, and vertical lift speed; Attitude and heading reference system: used to measure the pitch, roll, and heading of the aircraft, with accuracies of 2°, 2°, and 2° respectively; VHF radio: The working range is 117.975 - 137.0 MHz; 3) Storage and interface: Storage interface: The multifunctional display has 1 SD card interface for storage expansion; Communication interface: includes 2 Ethernet interfaces and 14 serial interfaces; Discrete IO interface: has 8 discrete IO interfaces.

[0095] In this embodiment, the avionics system design parameters are processed and the following operations are performed:

[0096] Obtain the avionics system design parameters;

[0097] Perform cleaning processing on the avionics system design parameters, including:

[0098] Perform consistency check on the avionics system design parameters;

[0099] According to the data consistency requirement, remove the inconsistent data in the avionics system design parameters that are useless for the digital model identification based on the avionics system;

[0100] Perform processing on invalid values and missing values in the avionics system design parameters;

[0101] According to the data validity and integrity requirements, remove the invalid values and missing values in the avionics system design parameters that are useless for the digital model identification based on the avionics system, and determine the avionics system design parameters that are useful for the digital model identification based on the avionics system;

[0102] It should be noted that by performing cleaning processing on the avionics system design parameters, the inconsistent data, invalid values and missing values in the avionics system design parameters that are useless for the digital model identification based on the avionics system can be removed.

[0103] Among them, data cleaning refers to the process of preprocessing data in data governance work. The purpose is to correct or delete the errors, duplicates and inconsistencies in the data to ensure the accuracy and integrity of the data. Through data cleaning, the data can be transformed into high-quality data, which is convenient for subsequent data analysis and use.

[0104] Obtain the avionics system design parameters that are useful for the digital model identification based on the avionics system;

[0105] Perform feature extraction on the avionics system design parameters that are useful for the digital model identification based on the avionics system;

[0106] Extract the features that can reflect the digital model identification based on the avionics system;

[0107] Determine the avionics system feature data.

[0108] It should be noted that by performing feature extraction on the avionics system design parameters that are useful for the digital model identification based on the avionics system, the avionics system feature data can be determined, which is convenient for subsequent determination of the influencing factors of the avionics system for digital model identification.

[0109] Specifically, for removing the invalid values and missing values in the avionics system design parameters that are useless for the digital model identification based on the avionics system, the following operations are performed:

[0110] Extract the number of data of the avionics system design parameters useful for the digital model identification of the avionics system after removing useless invalid values and missing values;

[0111] Compare the number of data with a preset data number threshold;

[0112] When the number of data is lower than the preset data number threshold, extract the weight values of the removed invalid values and missing values;

[0113] Extract the weight values of the valid values closest to the data generation time of the removed invalid values and missing values;

[0114] Use the weight values of the removed invalid values and missing values in combination with the weight values of the valid values closest to the data generation time of the removed invalid values and missing values to obtain a weight value threshold;

[0115] Among them, the weight value threshold is obtained through the following formula:

[0116]

[0117] Among them, S represents the weight value threshold; n represents the number of removed invalid values; m represents the number of removed missing values; w 01i represents the weight value of the i-th removed invalid value; w 01xi represents the weight value of the valid value closest to the data generation time of the i-th removed invalid value; w 02i represents the weight value of the i-th removed missing value; w 02xi represents the weight value of the valid value closest to the data generation time of the i-th removed missing value; E 01 and E 02 respectively represent the first adjustment coefficient and the second adjustment coefficient, and, the first adjustment coefficient is obtained through the following formula:

[0118]

[0119] Among them, E 01 represents the first adjustment coefficient; w 01z represents the median of the weight values of n removed invalid values; w 01xz represents the median of the weight values of the valid values closest to the data generation time corresponding to n removed invalid values;

[0120] At the same time, the second adjustment coefficient is obtained through the following formula:

[0121]

[0122] Among them, E 02 represents the second adjustment coefficient; w02z Represents the median of the weight values of m removed missing values; w 02xz Represents the median of the weight values of the valid values closest to the data generation time corresponding to the m removed missing values;

[0123] Compare the weight values corresponding to the invalid values and missing values with a preset weight value threshold, obtain the filling values corresponding to the invalid values and missing values through the comparison results, and use the filling values corresponding to the invalid values and missing values to fill the corresponding invalid values and missing values.

[0124] The technical effects of the above technical solution are as follows: By removing useless invalid values and missing values, the accuracy and reliability of the avionics system design parameter data used for the digital model identification of the avionics system are ensured. This helps to improve the accuracy and prediction ability of model identification. Conducting weight analysis and filling processing on missing and invalid data further enhances the integrity of the data and reduces model bias or errors caused by incomplete data. Through the comparison of the number of data with a preset threshold and further analysis based on the weight values, this technical solution can make more effective use of available data and avoid problems such as insufficient model training or inaccurate results caused by insufficient data. The setting of the weight value threshold and the calculation of the adjustment coefficient enable the importance and time proximity of different data points to be considered during data filling, thereby improving the overall utilization efficiency of the data. Through the weight analysis and filling processing of invalid values and missing values, this technical solution can enhance the robustness of the model, enabling it to maintain good performance in the face of incomplete or missing data. The setting of the weight value threshold and the introduction of the adjustment coefficient enable the model to more accurately reflect the actual distribution and characteristics of the data during data filling, thereby improving the generalization ability and adaptability of the model. This technical solution avoids the cumbersome manual data cleaning and filling processes through clear weight value calculation and filling value acquisition steps, improving the computational efficiency of data processing and model training. At the same time, through automated weight analysis and filling processing, the possibility of human intervention and errors is reduced, further improving the overall computational efficiency. This technical solution makes the data filling and model training processes more transparent and interpretable through a clear weight value calculation process and filling value acquisition method. This helps users understand the behavior and performance of the model and the impact of data on the model, thereby making more informed decisions and adjustments.

[0125] In summary, this technical solution can achieve multiple technical effects such as improving data integrity and accuracy, enhancing data utilization efficiency, strengthening model robustness, improving computational efficiency, and enhancing interpretability in terms of performance indicators.

[0126] Specifically, compare the weight values corresponding to the invalid values and missing values with a preset weight value threshold, obtain the filling values corresponding to the invalid values and missing values through the comparison results, and use the filling values corresponding to the invalid values and missing values to perform filling processing on the corresponding invalid values and missing values, and perform the following operations:

[0127] Compare the weight value of the invalid value with the weight value threshold, and extract the invalid value whose weight value exceeds the weight value threshold as the target invalid value;

[0128] Extract the valid values with the same weight value as each target invalid value from the valid numerical values as the first reference valid values;

[0129] Extract the data generation time interval between the first reference valid value and each target invalid value;

[0130] Use the data value of the first reference valid value combined with the data generation time interval between the first reference valid value and each target invalid value to obtain the filling value corresponding to each target invalid value;

[0131] Among them, the filling value corresponding to each target invalid value is obtained through the following formula:

[0132]

[0133] Where X w represents the filling value corresponding to each target invalid value; a represents the number of data of the first reference valid value corresponding to each target invalid value; X 01i represents the data value of the i-th first reference valid value; X 01i+1 represents the data value of the (i + 1)-th first reference valid value; X 01b represents the standard deviation of the data values of a first reference valid values; T g01i represents the data generation time interval between the i-th first reference valid value and each target invalid value;

[0134] Use the filling value corresponding to each target invalid value to perform filling processing on the target invalid value.

[0135] The technical effects of the above technical solution are as follows: By comparing the weight value of the invalid value with a preset weight value threshold and extracting the target invalid values exceeding the threshold for special processing, this technical solution can selectively fill the invalid values that are more important (i.e., have higher weights) for the model or analysis. This helps to improve the quality and reliability of the overall data set. Using the first reference valid numerical value with the same weight value as the target invalid value and combining the data generation time interval to obtain the filling value, this method takes into account the time series characteristics of the data and the relationship between adjacent data points. By integrating multiple factors (such as data values, number of data, standard deviation, and time interval), the calculation of the filling value is more accurate and can better reflect the possible true value of the target invalid value. Accurately filling the invalid values helps to reduce noise and outliers in the data set, thereby improving the performance of the model trained based on these data. A more accurate filling value means that the model can learn a more real data distribution and features, thus improving the accuracy of prediction or classification. This technical solution avoids the cumbersome manual data cleaning and filling process through clear weight value comparison and filling value calculation steps. Automated filling processing reduces the possibility of human intervention and errors, while improving the overall data processing efficiency. This technical solution can handle invalid values with different weights and different time intervals, showing good adaptability and flexibility. This means that it can be widely applied in different data sets and scenarios without requiring a large number of adjustments or modifications to the algorithm. The calculation process of the filling value is based on clear formulas and factors (such as data values, number of data, standard deviation, and time interval), which makes the filling process more transparent and interpretable. Users or developers can more easily understand the source and calculation process of the filling value, thus having a deeper understanding of the data set and the model.

[0136] In summary, this technical solution can achieve multiple technical effects such as improving data quality, enhancing the accuracy of filling values, optimizing model performance, increasing calculation efficiency, strengthening adaptability and flexibility, and improving interpretability in terms of performance indicators. These effects work together in the data analysis and model training processes, helping to improve the overall data processing efficiency and model performance.

[0137] Specifically, compare the weight values corresponding to the invalid values and missing values with a preset weight value threshold, obtain the filling values corresponding to the invalid values and missing values through the comparison results, and use the filling values corresponding to the invalid values and missing values to fill the corresponding invalid values and missing values, and also perform the following operations:

[0138] Compare the weight value of the missing value with the weight value threshold, and extract the missing values corresponding to the weight values exceeding the weight value threshold as target missing values;

[0139] Extract valid values equal to the weight value of each of the target missing values from the valid values as the second reference valid values;

[0140] Extract the filled target invalid values equal to the weight value of the target missing value as the third reference valid values;

[0141] Extract the data generation time intervals between the second reference valid values and the third reference valid values and each target missing value;

[0142] Use the second reference valid values and the third reference valid values in combination with the data generation time intervals between the second reference valid values and the third reference valid values and each target missing value to obtain the filling values corresponding to each target missing value;

[0143] Among them, the filling value corresponding to each target missing value is obtained through the following formula:

[0144]

[0145] Among them, X q represents the filling value corresponding to each target missing value; b represents the number of data of the second reference valid values; c represents the number of data of the third reference valid values; X 02i represents the data value of the i-th second reference valid value; X wi represents the data value of the i-th third reference valid value; T g02i represents the data generation time interval between the i-th second reference valid value and each target missing value; T g03i represents the data generation time interval between the i-th third reference valid value and each target missing value; X 02z represents the median of the data values of b second reference valid values; X wz represents the median of the data values of c third reference valid values; X wb represents the standard deviation of the data values of c third reference valid values; X wp represents the average of the data values of c third reference valid values; X 02b represents the standard deviation of the data values of b second reference valid values; X 02p represents the average of the data values of b second reference valid values;

[0146] Use the filling value corresponding to each target missing value to fill the target missing value.

[0147] The technical effects of the above technical solution are as follows: By comparing the weight value of the missing value with a preset weight value threshold and extracting the target missing values exceeding the threshold for filling processing, this technical solution can ensure the integrity of important data. This helps to reduce analysis bias or model performance degradation caused by data missing. Using the second reference valid value with the same weight value as the target missing value and the filled target invalid value (as the third reference valid value), and combining the data generation time interval to calculate the filling value, this method comprehensively considers multiple factors, including data values, the number of data, standard deviation, average value, and time interval. This comprehensive consideration makes the calculation of the filling value more accurate and can more accurately reflect the possible true value of the target missing value. Precise filling of missing values helps to reduce noise and outliers in the dataset, thereby improving the robustness of the model trained based on these data. A more accurate filling value means that the model can better handle incomplete data and exhibit more stable performance in practical applications. This technical solution realizes automated data filling processing through clear weight value comparison and filling value calculation steps. This reduces the need for manual intervention and improves the overall efficiency of data processing. At the same time, this solution can handle datasets of different scales and complexities, showing good scalability. This technical solution can handle missing values with different weights and different time intervals, showing good adaptability and flexibility. This means that it can be widely applied in different datasets and scenarios without the need for extensive adjustment or modification of the algorithm. By calculating the filling value and applying it, this technical solution can also be part of data quality monitoring and improvement. By evaluating the effect of the filling value, problems existing in the dataset can be further understood and corresponding measures can be taken for improvement. The calculation process of the filling value is based on clear formulas and multiple factors (such as data values, the number of data, standard deviation, average value, and time interval), which makes the filling process more transparent and interpretable. Users or developers can more easily understand the source and calculation process of the filling value, thereby having a deeper understanding of the dataset and the model.

[0148] In summary, this technical solution can achieve multiple technical effects such as enhancing data integrity, improving the accuracy of filling values, enhancing model robustness, improving calculation efficiency and scalability, enhancing adaptability and flexibility, and promoting data quality monitoring and improvement in terms of performance indicators. These effects act together on the data analysis and model training processes, helping to improve the overall data processing efficiency and model performance.

[0149] In this embodiment, to determine the influencing factors of the avionics system for digital model identification, the following operations are performed:

[0150] According to the structure and functions of the avionics system digital model, combined with the actual flight conditions of the aircraft, define the identification rules, check whether the avionics system digital model can correctly implement all expected functions, comprehensively consider the factors that will affect the behavior of the avionics system, and determine the avionics system influencing factors for digital model identification;

[0151] Among them, the avionics system influencing factors for digital model identification include: speed, altitude, load, temperature, pressure, and electromagnetic interference.

[0152] S2: Perform simulation analysis on the avionics system digital model based on different avionics system influencing factors for digital model identification, and determine the simulation analysis results of the avionics system digital model;

[0153] In this embodiment, to determine the simulation analysis results of the avionics system digital model, perform the following operations:

[0154] Obtain the avionics system influencing factors for digital model identification;

[0155] Input different avionics system influencing factors for digital model identification into the avionics system digital model;

[0156] Perform simulation analysis on the avionics system digital model based on different avionics system influencing factors for digital model identification. By comparing the performance of the avionics system under different avionics system influencing factors, determine the simulation analysis results of the avionics system digital model.

[0157] S3: Based on the avionics system digital model simulation analysis standard, perform digital model identification on the simulation analysis results of the avionics system digital model to determine the digital model identification results of the avionics system;

[0158] In this embodiment, to determine the digital model identification results of the avionics system, perform the following operations:

[0159] According to the digital model identification requirements of the avionics system, preset the avionics system digital model simulation analysis standard in advance and store the preset avionics system digital model simulation analysis standard;

[0160] According to the digital model identification requirements of the avionics system, index the stored avionics system digital model simulation analysis standard, and retrieve the indexed avionics system digital model simulation analysis standard;

[0161] Based on the avionics system digital model simulation analysis standard, perform digital model identification on the simulation analysis results of the avionics system digital model to determine the digital model identification results of the avionics system.

[0162] In this embodiment, based on the avionics system digital model simulation analysis standard, performing digital model identification on the simulation analysis results of the avionics system digital model includes:

[0163] When the simulation analysis result of the avionics system digital model is within the avionics system digital model simulation analysis standard range, the identification result of the avionics system digital model is that the avionics system digital model is normal and can correctly implement all expected functions;

[0164] When the simulation analysis result of the avionics system digital model is not within the avionics system digital model simulation analysis standard range, the identification result of the avionics system digital model is that the avionics system digital model is abnormal and cannot correctly implement all expected functions.

[0165] It should be noted that based on the avionics system digital model simulation analysis standard, the digital model identification of the avionics system digital model simulation analysis result can determine the avionics system digital model identification result. Based on the avionics system digital model identification result, an avionics system digital model identification optimization report can be generated to intelligently guide managers to adjust and optimize the avionics system digital model, timely solve the abnormal problems of the avionics system digital model, effectively identify the digital model of the avionics system, timely discover and solve abnormal problems, and improve the use effect.

[0166] S4: Based on the avionics system digital model identification result, generate an avionics system digital model identification optimization report to intelligently guide managers to adjust and optimize the avionics system digital model, and timely solve the abnormal problems of the avionics system digital model.

[0167] In this embodiment, to intelligently guide managers to adjust and optimize the avionics system digital model, the following operations are performed:

[0168] Obtain the avionics system digital model identification result;

[0169] Based on the avionics system digital model identification result, conduct mining analysis on the avionics system digital model to generate an avionics system digital model identification optimization report;

[0170] Transmit the avionics system digital model identification optimization report to managers in a visual form to intelligently guide managers to adjust and optimize the avionics system digital model, and timely solve the abnormal problems of the avionics system digital model.

[0171] It should be noted that, in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0172] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A digital model identification method based on an avionics system, characterized in that It includes the following steps: S1: Use modeling software and mathematical tools to construct a digital model of the avionics system, define identification rules, and determine the influencing factors of the avionics system identified by the digital model; S2: Based on the influencing factors of the avionics system identified by different digital models, conduct simulation analysis on the digital model of the avionics system to determine the simulation analysis results of the digital model of the avionics system; S3: Based on the digital model simulation analysis standard of the avionics system, conduct digital model identification on the simulation analysis results of the digital model of the avionics system to determine the digital model identification results of the avionics system; S4: Based on the digital model identification results of the avionics system, generate an optimization report for the digital model identification of the avionics system, intelligently guide managers to adjust and optimize the digital model of the avionics system, and timely solve the abnormal problems of the digital model of the avionics system; In the above S1, when constructing the digital model of the avionics system, the following operations are performed: Collect the hardware specifications and software configuration parameters of the avionics system to determine the design parameters of the avionics system; Process the design parameters of the avionics system to determine the characteristic data of the avionics system; Based on the characteristic data of the avionics system, and using modeling software and mathematical tools, conduct three-dimensional modeling on the avionics system to determine the digital model of the avionics system; among them, collect the design parameters of the avionics system and process the design parameters of the avionics system; Remove the invalid values and missing values that are useless for the digital model identification of the avionics system from the design parameters of the avionics system, and perform the following operations: After removing the useless invalid values and missing values, extract the number of data of the design parameters of the avionics system that are useful for the digital model identification of the avionics system; Compare the number of data with a preset threshold of the number of data; When the number of data is lower than the preset threshold of the number of data, extract the weight values of the removed invalid values and missing values; Extract the weight values of the valid values that are closest to the data generation time of the removed invalid values and missing values; Use the weight values of the removed invalid values and missing values combined with the weight values of the valid values that are closest to the data generation time of the removed invalid values and missing values to obtain a weight value threshold; The weight value threshold is obtained through the following formula: Wherein, S represents the weight value threshold; n represents the number of invalid values to be removed; m represents the number of missing values to be removed; w 01i represents the weight value of the i-th invalid value to be removed; w 01xi represents the weight value of the valid value closest to the data generation time of the i-th invalid value to be removed; w 02i represents the weight value of the i-th missing value to be removed; w 02xi represents the weight value of the valid value closest to the data generation time of the i-th missing value to be removed; E 01 and E 02 respectively represent a first adjustment coefficient and a second adjustment coefficient, and the first adjustment coefficient is obtained by the following formula: Among them, E 01 represents the first adjustment coefficient; w 01z represents the median of the weight values of n removed invalid values; w 01xz represents the median of the weight values of the valid values closest to the data generation time corresponding to n removed invalid values; Meanwhile, the second adjustment coefficient is obtained through the following formula: Among them, E 02 represents the second adjustment coefficient; w 02z represents the median value of the weight values of m removed missing values; w 02xz represents the median value of the weight values of the valid numerical values closest to the data generation time corresponding to m removed missing values; Compare the weight values corresponding to the invalid values and missing values with the preset weight value threshold, obtain the filling values corresponding to the invalid values and missing values through the comparison results, and use the filling values corresponding to the invalid values and missing values to perform filling processing on the corresponding invalid values and missing values, and perform the following operations: Compare the weight value of the invalid value with the weight value threshold, and extract the invalid values whose weight values exceed the weight value threshold as target invalid values; Extract the valid values with the same weight values as each target invalid value from the valid values as the first reference valid values; Extract the data generation time intervals between the first reference valid values and each target invalid value; Use the data values of the first reference valid values combined with the data generation time intervals between the first reference valid values and each target invalid value to obtain the filling values corresponding to each target invalid value; among them, the filling values corresponding to each target invalid value are obtained through the following formula: Among them, X w represents the filling value corresponding to each target invalid value; a represents the number of data of the first reference valid value corresponding to each target invalid value; X 01i represents the data value of the i-th first reference valid value; X 01i+1 represents the data value of the (i + 1)-th first reference valid value; X 01b represents the standard deviation of the data values of a first reference valid values; T g01i represents the data generation time interval between the i-th first reference valid value and each target invalid value; Fill the target invalid values with the filling values corresponding to each of the target invalid values.

2. The digital model identification method based on an avionics system according to claim 1, wherein In S1, process the avionics system design parameters and perform the following operations: Obtain the avionics system design parameters; Clean the avionics system design parameters, including: Check the consistency of the avionics system design parameters; According to the data consistency requirements, remove the inconsistent data in the avionics system design parameters that are useless for the identification of the digital model based on the avionics system; Process the invalid values and missing values in the avionics system design parameters; According to the data validity and integrity requirements, remove the invalid values and missing values in the avionics system design parameters that are useless for the identification of the digital model based on the avionics system, and determine the avionics system design parameters that are useful for the identification of the digital model based on the avionics system; Obtain the avionics system design parameters that are useful for the identification of the digital model based on the avionics system; Extract the features of the avionics system design parameters that are useful for the identification of the digital model based on the avionics system; Extract the features that can reflect the identification of the digital model based on the avionics system; Determine the avionics system characteristic data.

3. The digital model identification method based on an avionics system according to claim 2, wherein Compare the weight values corresponding to the invalid values and missing values with the preset weight value threshold, obtain the filling values corresponding to the invalid values and missing values through the comparison results, and use the filling values corresponding to the invalid values and missing values to fill the corresponding invalid values and missing values, and also perform the following operations: Compare the weight value of the missing value with the weight value threshold, and extract the missing values whose weight values exceed the weight value threshold as the target missing values; Extract the valid values with the same weight value as each target missing value from the valid values as the second reference valid values; Extract the filled target invalid values with the same weight value as the target missing value as the third reference valid values; Extract the data generation time intervals between the second reference valid values and the third reference valid values and each target missing value; Use the second reference valid values and the third reference valid values and the data generation time intervals between the second reference valid values and the third reference valid values and each target missing value to obtain the filling values corresponding to each target missing value; Among them, the filling values corresponding to each target missing value are obtained through the following formula: Among them, X q represents the filling value corresponding to each target missing value; b represents the number of data of the second reference valid value; c represents the number of data of the third reference valid value; X 02i represents the data value of the i-th second reference valid value; X wi represents the data value of the i-th third reference valid value; T g02i represents the data generation time interval between the i-th second reference valid value and each target missing value; T g03i represents the data generation time interval between the i-th third reference valid value and each target missing value; X 02z represents the median of the data values of b second reference valid values; X wz represents the median of the data values of c third reference valid values; X wb represents the standard deviation of the data values of c third reference valid values; X wp represents the average value of the data values of c third reference valid values; X 02b represents the standard deviation of the data values of b second reference valid values; X 02p represents the average value of the data values of b second reference valid values; Fill the target missing values with the filling values corresponding to each of the target missing values.

4. The digital model identification method based on an avionics system according to claim 3, wherein In S1, determine the influencing factors of the avionics system for digital model identification and perform the following operations: According to the structure and function of the avionics system digital model, combined with the actual flight situation of the aircraft, define the identification rules, check whether the avionics system digital model can correctly implement all expected functions, and comprehensively consider which factors will affect the behavior of the avionics system to determine the influencing factors of the avionics system for digital model identification; Among them, the influencing factors of the avionics system for digital model identification include: speed, altitude, load, temperature, pressure, and electromagnetic interference.

5. The digital model identification method based on an avionics system according to claim 4, wherein In S2, determine the simulation analysis results of the avionics system digital model and perform the following operations: Obtain the influencing factors of the avionics system for digital model identification; Input the influencing factors of the avionics system identified by different digital models into the avionics system digital model; Based on the influencing factors of the avionics system identified by different digital models, conduct simulation analysis on the avionics system digital model. By comparing the performance of the avionics system under different influencing factors of the avionics system, determine the simulation analysis results of the avionics system digital model.

6. The digital model identification method based on an avionics system according to claim 5, wherein In step S3, to determine the identification result of the avionics system digital model, perform the following operations: According to the digital model identification requirements of the avionics system, preset the simulation analysis standard of the avionics system digital model in advance and store the preset simulation analysis standard of the avionics system digital model; According to the digital model identification requirements of the avionics system, index the stored simulation analysis standard of the avionics system digital model and retrieve the indexed simulation analysis standard of the avionics system digital model; Based on the simulation analysis standard of the avionics system digital model, conduct digital model identification on the simulation analysis results of the avionics system digital model to determine the identification result of the avionics system digital model; When the simulation analysis results of the avionics system digital model are within the range of the simulation analysis standard of the avionics system digital model, the identification result of the avionics system digital model is that the avionics system digital model is normal and can correctly implement all expected functions; When the simulation analysis results of the avionics system digital model are not within the range of the simulation analysis standard of the avionics system digital model, the identification result of the avionics system digital model is that the avionics system digital model is abnormal and cannot correctly implement all expected functions.

7. The digital model identification method based on an avionics system according to claim 6, wherein In step S4, to intelligently guide the management personnel to adjust and optimize the avionics system digital model, perform the following operations: Obtain the identification result of the avionics system digital model; Based on the identification result of the avionics system digital model, conduct mining analysis on the avionics system digital model to generate an identification optimization report of the avionics system digital model; Transmit the identification optimization report of the avionics system digital model to the management personnel in a visual form, intelligently guide the management personnel to adjust and optimize the avionics system digital model, and timely solve the abnormal problems of the avionics system digital model.

Images